GitLab

- In handleSmartRetry, use the actual upstream retryDelay to set model
  rate limit duration instead of always using the 30s default
- Return info.RetryDelay from shouldTriggerAntigravitySmartRetry when
  shouldRateLimitModel=true, so callers know the actual delay
- Extract getDefaultRateLimitDuration() and resolveResetTime() helpers
  to reduce duplication in handleUpstreamError 429 handling
- Improve debug logging with upstream_retry_delay and response body

Upstream accounts now use the standard APIKey type instead of a dedicated
upstream type. GetBaseURL() and new GetGeminiBaseURL() automatically append
/antigravity for Antigravity platform APIKey accounts, eliminating the need
for separate upstream forwarding methods.

- Remove ForwardUpstream, ForwardUpstreamGemini, testUpstreamConnection
- Remove upstream branch guards in Forward/ForwardGemini/TestConnection
- Add migration 052 to convert existing upstream accounts to apikey
- Update frontend CreateAccountModal to create apikey type
- Add unit tests for GetBaseURL and GetGeminiBaseURL

ForwardUpstream/ForwardUpstreamGemini should pipe the upstream response
directly to the client (headers + body), not parse it as SSE stream.

Replace manual header setting (Content-Type, anthropic-version, anthropic-beta)
with full client header passthrough in ForwardUpstream/ForwardUpstreamGemini.
Only authentication headers (Authorization, x-api-key) are overridden with
upstream account credentials. Hop-by-hop headers are excluded.

Add unit tests covering header passthrough, auth override, and hop-by-hop filtering.

v0.1.74 merged upstream accounts into the OAuth path, causing requests
to hit the wrong protocol and endpoint. Add three upstream-specific
methods (testUpstreamConnection, ForwardUpstream, ForwardUpstreamGemini)
that use base_url + apiKey auth and passthrough the original body, while
reusing the existing response handling and error/retry logic.

- Change antigravitySmartRetryMaxAttempts from 3 to 1 to prevent
  repeated rate limiting and long waits
- Clear sticky session binding (DeleteSessionAccountID) after smart
  retry exhaustion, so subsequent requests don't hit the same
  rate-limited account
- Add flow diagrams to Forward/ForwardGemini doc comments
- Add comprehensive unit tests covering:
  - Sticky session cleared on retry failure (429, 503, network error)
  - Sticky session NOT cleared on retry success
  - Sticky session NOT cleared for non-sticky requests (empty hash)
  - Sticky session NOT cleared on long delay path (handled by handler)
  - Nil cache safety (no panic)
  - MaxAttempts constant verification
  - End-to-end retryLoop → switchError propagation with session clear

- avoid panic by using safe UUID prefix truncation in Gemini digest fallback logs\n- remove unconditional Antigravity 429 full-body debug logs and honor log truncation config\n- align Antigravity quick preset mappings to opus 4.6-thinking targets only\n- restore scope rate-limit aggregation/output in ops availability stats

Remove threshold-based waiting in both sticky session and antigravity
pre-check paths. When a model is rate-limited, immediately clear the
sticky session and switch accounts instead of waiting for short durations.

1. Frontend: replace hardcoded antigravityDefaultMappings with async
   fetch from GET /admin/accounts/antigravity/default-model-mapping,
   eliminating the duplicate data source that caused frontend/backend
   mapping inconsistency.

2. Backend: convert handleSmartRetry and antigravityRetryLoop from
   standalone functions to AntigravityGatewayService methods, enabling
   Redis cache sync (updateAccountModelRateLimitInCache) after both
   rate-limit write paths — long-delay branch and retry-exhausted branch.

- GetAccessToken: add upstream branch to read api_key from credentials
- shouldTriggerAntigravitySmartRetry: relax check from IsOAuth to Platform-based
- isModelSupportedByAccount/WithContext: replace IsAntigravityModelSupported
  whitelist with mapAntigravityModel for unified scheduling/forwarding logic
- mapAntigravityModel: fix edge case where wildcard target equals request model
- Update tests for new behavior and add custom model_mapping test cases

Key changes:
- Upgrade model mapping: Opus 4.5 → Opus 4.6-thinking with precise matching
- Unified rate limiting: scope-level → model-level with Redis snapshot sync
- Load-balanced scheduling by call count with smart retry mechanism
- Force cache billing support
- Model identity injection in prompts with leak prevention
- Thinking mode auto-handling (max_tokens/budget_tokens fix)
- Frontend: whitelist mode toggle, model mapping validation, status indicators
- Gemini session fallback with Redis Trie O(L) matching
- Ops: enhanced concurrency monitoring, account availability, retry logic
- Migration scripts: 049-051 for model mapping unification

The default fallback cooldown when rate limit reset time cannot be
parsed was 5 minutes, which is too aggressive and causes accounts
to be unnecessarily locked out. Reduce to 30 seconds for faster
recovery. Config override still works (unit remains minutes).

支持管理员配置上游错误如何返回给客户端：
- 新增 ErrorPassthroughRule 数据模型和 Ent Schema
- 实现规则的 CRUD API（/admin/error-passthrough-rules）
- 支持按错误码、关键词匹配，支持 any/all 匹配模式
- 支持按平台过滤（anthropic/openai/gemini/antigravity）
- 支持透传或自定义响应状态码和错误消息
- 实现两级缓存（Redis + 本地内存）和多实例同步
- 集成到 gateway_handler 的错误处理流程
- 新增前端管理界面组件
- 新增单元测试覆盖核心匹配逻辑

优化：
- 移除 refreshLocalCache 中的冗余排序（数据库已排序）
- 后端 Validate() 增加匹配条件非空校验

问题描述：
使用扩展思考功能时，偶现以下错误：
"thinking or redacted_thinking blocks in the latest assistant message cannot be modified"

根因分析：
当代理服务修改请求体中的某些字段时（如 metadata.user_id、model），
使用 map[string]any 解析整个 JSON 后重新序列化，导致：
1. 字段顺序改变（Go map 序列化按字母排序）
2. 数字格式变化（如 1.0 → 1）
3. Unicode 转义变化

Claude API 对 thinking 块进行字节级验证，任何变化都会触发错误。

修复内容：
1. identity_service.go - RewriteUserID/RewriteUserIDWithMasking
   使用 json.RawMessage 保留其他字段的原始字节

2. gateway_service.go - replaceModelInBody
   使用 json.RawMessage 保留其他字段的原始字节

3. gateway_service.go - normalizeClaudeOAuthRequestBody
   保留 messages 的原始字节，跳过包含 thinking 块的消息修改

4. gateway_service.go - isThinkingBlockSignatureError
   添加 "cannot be modified" 错误检测，触发自动重试

5. antigravity_gateway_service.go - isSignatureRelatedError
   添加 "cannot be modified" 错误检测
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

将 GATEWAY_ANTIGRAVITY_429_SCOPE_LIMIT 的默认值从关闭改为开启。
当 Gemini 模型触发 429 限流时，只会限制对应的配额域（gemini_text），
而 Claude 和 gemini_image 仍可继续使用，提高账号利用率。

Antigravity 上游不再支持 gemini-2.5 系列，统一映射到 gemini-3：
- gemini-2.5-flash → gemini-3-flash
- gemini-2.5-flash-lite → gemini-3-flash
- gemini-2.5-flash-thinking → gemini-3-flash
- gemini-2.5-flash-image → gemini-3-pro-image
- gemini-2.5-pro → gemini-3-pro-high
- gemini-2.5-pro-preview → gemini-3-pro-high
- gemini-2.5-pro-exp → gemini-3-pro-high

Add prefix mapping rules for gemini-2.5-pro variants:
- gemini-2.5-pro -> gemini-3-pro-high
- gemini-2.5-pro-preview -> gemini-3-pro-high
- gemini-2.5-pro-exp -> gemini-3-pro-high

Gemini API 不接受 contents 数组中 parts 为空的消息，会返回 400 INVALID_ARGUMENT 错误。
添加 filterEmptyPartsFromGeminiRequest 函数在转发前过滤这类消息。

影响范围：ForwardGemini (antigravity) 和 ForwardNative (gemini)

- Group 新增 mcp_xml_inject 字段，控制 Antigravity 平台的 MCP XML 协议注入
- 默认启用，可在分组设置中关闭
- 修复 GetByKeyForAuth 遗漏查询 mcp_xml_inject 字段导致认证缓存值始终为 false 的问题

- 修复 TransformGeminiToClaude 的 JSON 解析逻辑，当 V1InternalResponse
  解析成功但 candidates 为空时，尝试直接解析为 GeminiResponse 格式
- 修复 handleClaudeStreamToNonStreaming 收集流式响应的逻辑，累积所有
  chunks 的内容而不是只保留最后一个（最后一个 chunk 通常 text 为空）
- 新增 mergeCollectedPartsToResponse 函数，合并所有类型的 parts
  （text、thinking、functionCall、inlineData），保持原始顺序
- 连续的普通 text parts 合并为一个，thinking/functionCall/inlineData 保持原样

新增环境变量：
- GATEWAY_ANTIGRAVITY_MAX_RETRIES_CLAUDE
- GATEWAY_ANTIGRAVITY_MAX_RETRIES_GEMINI_TEXT
- GATEWAY_ANTIGRAVITY_MAX_RETRIES_GEMINI_IMAGE

未设置时回退到平台级 GATEWAY_ANTIGRAVITY_MAX_RETRIES

主要变更：
1. 重构代码结构：
   - 将 CleanJSONSchema 及其相关辅助函数从 request_transformer.go 提取到独立的 schema_cleaner.go 文件中，实现逻辑解耦。

2. 逻辑优化与修正：
   - 参考 Antigravity-Manager (json_schema.rs) 的实现逻辑，修正了 Schema 清洗策略。

主要变更：
1. 重构代码结构：
   - 将 CleanJSONSchema 及其相关辅助函数从 request_transformer.go 提取到独立的 schema_cleaner.go 文件中，实现逻辑解耦。

2. 逻辑优化与修正：
   - 参考 Antigravity-Manager (json_schema.rs) 的实现逻辑，修正了 Schema 清洗策略。